Repository navigation
Expand file tree
/
Copy pathbase.py
More file actions
1452 lines (1218 loc) · 57.3 KB
/
Copy pathbase.py
File metadata and controls
1452 lines (1218 loc) · 57.3 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# Copyright (C) 2008, 2009 Michael Trier (mtrier@gmail.com) and contributors
#
# This module is part of GitPython and is released under the
# 3-Clause BSD License: https://opensource.org/license/bsd-3-clause/
"""Module containing IndexFile, an Index implementation facilitating all kinds of index
manipulations such as querying and merging."""
import contextlib
import datetime
import glob
from io import BytesIO
import os
from stat import S_ISLNK
import subprocess
import tempfile
from git.compat import (
force_bytes,
defenc,
)
from git.exc import GitCommandError, CheckoutError, GitError, InvalidGitRepositoryError
from git.objects import (
Blob,
Submodule,
Tree,
Object,
Commit,
)
from git.objects.util import Serializable
from git.util import (
LazyMixin,
LockedFD,
join_path_native,
file_contents_ro,
to_native_path_linux,
unbare_repo,
to_bin_sha,
)
from gitdb.base import IStream
from gitdb.db import MemoryDB
import git.diff as git_diff
import os.path as osp
from .fun import (
entry_key,
write_cache,
read_cache,
aggressive_tree_merge,
write_tree_from_cache,
stat_mode_to_index_mode,
S_IFGITLINK,
run_commit_hook,
)
from .typ import (
BaseIndexEntry,
IndexEntry,
StageType,
)
from .util import TemporaryFileSwap, post_clear_cache, default_index, git_working_dir
# typing -----------------------------------------------------------------------------
from typing import (
Any,
BinaryIO,
Callable,
Dict,
Generator,
IO,
Iterable,
Iterator,
List,
NoReturn,
Sequence,
TYPE_CHECKING,
Tuple,
Type,
Union,
)
from git.types import Commit_ish, PathLike
if TYPE_CHECKING:
from subprocess import Popen
from git.repo import Repo
from git.refs.reference import Reference
from git.util import Actor
Treeish = Union[Tree, Commit, str, bytes]
# ------------------------------------------------------------------------------------
__all__ = ("IndexFile", "CheckoutError", "StageType")
@contextlib.contextmanager
def _named_temporary_file_for_subprocess(directory: PathLike) -> Generator[str, None, None]:
"""Create a named temporary file git subprocesses can open, deleting it afterward.
:param directory: The directory in which the file is created.
:return: A context manager object that creates the file and provides its name on
entry, and deletes it on exit.
"""
if os.name == "nt":
fd, name = tempfile.mkstemp(dir=directory)
os.close(fd)
try:
yield name
finally:
os.remove(name)
else:
with tempfile.NamedTemporaryFile(dir=directory) as ctx:
yield ctx.name
class IndexFile(LazyMixin, git_diff.Diffable, Serializable):
"""An Index that can be manipulated using a native implementation in order to save
git command function calls wherever possible.
This provides custom merging facilities allowing to merge without actually changing
your index or your working tree. This way you can perform own test-merges based
on the index only without having to deal with the working copy. This is useful
in case of partial working trees.
``Entries``
The index contains an entries dict whose keys are tuples of type IndexEntry
to facilitate access.
You may read the entries dict or manipulate it using IndexEntry instance, i.e.::
index.entries[index.entry_key(index_entry_instance)] = index_entry_instance
Make sure you use index.write() once you are done manipulating the index directly
before operating on it using the git command.
"""
__slots__ = ("repo", "version", "entries", "_extension_data", "_file_path")
_VERSION = 2 # Latest version we support.
S_IFGITLINK = S_IFGITLINK # A submodule.
def __init__(self, repo: "Repo", file_path: Union[PathLike, None] = None) -> None:
"""Initialize this Index instance, optionally from the given ``file_path``.
If no file_path is given, we will be created from the current index file.
If a stream is not given, the stream will be initialized from the current
repository's index on demand.
"""
self.repo = repo
self.version = self._VERSION
self._extension_data = b""
self._file_path: PathLike = file_path or self._index_path()
def _set_cache_(self, attr: str) -> None:
if attr == "entries":
try:
fd = os.open(self._file_path, os.O_RDONLY)
except OSError:
# In new repositories, there may be no index, which means we are empty.
self.entries: Dict[Tuple[PathLike, StageType], IndexEntry] = {}
return
# END exception handling
try:
stream = file_contents_ro(fd, stream=True, allow_mmap=True)
finally:
os.close(fd)
self._deserialize(stream)
else:
super()._set_cache_(attr)
def _index_path(self) -> PathLike:
if self.repo.git_dir:
return join_path_native(self.repo.git_dir, "index")
else:
raise GitCommandError("No git directory given to join index path")
@property
def path(self) -> PathLike:
""":return: Path to the index file we are representing"""
return self._file_path
def _delete_entries_cache(self) -> None:
"""Safely clear the entries cache so it can be recreated."""
try:
del self.entries
except AttributeError:
# It failed in Python 2.6.5 with AttributeError.
# FIXME: Look into whether we can just remove this except clause now.
pass
# END exception handling
# { Serializable Interface
def _deserialize(self, stream: IO) -> "IndexFile":
"""Initialize this instance with index values read from the given stream."""
self.version, self.entries, self._extension_data, _conten_sha = read_cache(stream)
return self
def _entries_sorted(self) -> List[IndexEntry]:
""":return: list of entries, in a sorted fashion, first by path, then by stage"""
return sorted(self.entries.values(), key=lambda e: (e.path, e.stage))
def _serialize(self, stream: IO, ignore_extension_data: bool = False) -> "IndexFile":
entries = self._entries_sorted()
extension_data = self._extension_data # type: Union[None, bytes]
if ignore_extension_data:
extension_data = None
write_cache(entries, stream, extension_data)
return self
# } END serializable interface
def write(
self,
file_path: Union[None, PathLike] = None,
ignore_extension_data: bool = False,
) -> None:
"""Write the current state to our file path or to the given one.
:param file_path:
If None, we will write to our stored file path from which we have
been initialized. Otherwise we write to the given file path.
Please note that this will change the file_path of this index to
the one you gave.
:param ignore_extension_data:
If True, the TREE type extension data read in the index will not
be written to disk. NOTE that no extension data is actually written.
Use this if you have altered the index and
would like to use git-write-tree afterwards to create a tree
representing your written changes.
If this data is present in the written index, git-write-tree
will instead write the stored/cached tree.
Alternatively, use IndexFile.write_tree() to handle this case
automatically.
"""
# Make sure we have our entries read before getting a write lock.
# Otherwise it would be done when streaming. This can happen if one
# doesn't change the index, but writes it right away.
self.entries
lfd = LockedFD(file_path or self._file_path)
stream = lfd.open(write=True, stream=True)
try:
self._serialize(stream, ignore_extension_data)
except BaseException:
lfd.rollback()
raise
lfd.commit()
# Make sure we represent what we have written.
if file_path is not None:
self._file_path = file_path
@post_clear_cache
@default_index
def merge_tree(self, rhs: Treeish, base: Union[None, Treeish] = None) -> "IndexFile":
"""Merge the given rhs treeish into the current index, possibly taking
a common base treeish into account.
As opposed to the :func:`IndexFile.from_tree` method, this allows you to use an
already existing tree as the left side of the merge.
:param rhs:
Treeish reference pointing to the 'other' side of the merge.
:param base:
Optional treeish reference pointing to the common base of 'rhs' and this
index which equals lhs.
:return:
self (containing the merge and possibly unmerged entries in case of
conflicts)
:raise GitCommandError:
If there is a merge conflict. The error will be raised at the first
conflicting path. If you want to have proper merge resolution to be done by
yourself, you have to commit the changed index (or make a valid tree from
it) and retry with a three-way index.from_tree call.
"""
# -i : ignore working tree status
# --aggressive : handle more merge cases
# -m : do an actual merge
args: List[Union[Treeish, str]] = ["--aggressive", "-i", "-m"]
if base is not None:
args.append(base)
args.append(rhs)
self.repo.git.read_tree(args)
return self
@classmethod
def new(cls, repo: "Repo", *tree_sha: Union[str, Tree]) -> "IndexFile":
"""Merge the given treeish revisions into a new index which is returned.
This method behaves like ``git-read-tree --aggressive`` when doing the merge.
:param repo: The repository treeish are located in.
:param tree_sha:
20 byte or 40 byte tree sha or tree objects.
:return:
New IndexFile instance. Its path will be undefined.
If you intend to write such a merged Index, supply an alternate file_path
to its 'write' method.
"""
tree_sha_bytes: List[bytes] = [to_bin_sha(str(t)) for t in tree_sha]
base_entries = aggressive_tree_merge(repo.odb, tree_sha_bytes)
inst = cls(repo)
# Convert to entries dict.
entries: Dict[Tuple[PathLike, int], IndexEntry] = dict(
zip(
((e.path, e.stage) for e in base_entries),
(IndexEntry.from_base(e) for e in base_entries),
)
)
inst.entries = entries
return inst
@classmethod
def from_tree(cls, repo: "Repo", *treeish: Treeish, **kwargs: Any) -> "IndexFile":
"""Merge the given treeish revisions into a new index which is returned.
The original index will remain unaltered.
:param repo:
The repository treeish are located in.
:param treeish:
One, two or three Tree Objects, Commits or 40 byte hexshas. The result
changes according to the amount of trees.
If 1 Tree is given, it will just be read into a new index
If 2 Trees are given, they will be merged into a new index using a
two way merge algorithm. Tree 1 is the 'current' tree, tree 2 is the 'other'
one. It behaves like a fast-forward.
If 3 Trees are given, a 3-way merge will be performed with the first tree
being the common ancestor of tree 2 and tree 3. Tree 2 is the 'current' tree,
tree 3 is the 'other' one.
:param kwargs:
Additional arguments passed to git-read-tree.
:return:
New IndexFile instance. It will point to a temporary index location which
does not exist anymore. If you intend to write such a merged Index, supply
an alternate file_path to its 'write' method.
:note:
In the three-way merge case, --aggressive will be specified to automatically
resolve more cases in a commonly correct manner. Specify trivial=True as kwarg
to override that.
As the underlying git-read-tree command takes into account the current
index, it will be temporarily moved out of the way to prevent any unexpected
interference.
"""
if len(treeish) == 0 or len(treeish) > 3:
raise ValueError("Please specify between 1 and 3 treeish, got %i" % len(treeish))
arg_list: List[Union[Treeish, str]] = []
# Ignore that the working tree and index possibly are out of date.
if len(treeish) > 1:
# Drop unmerged entries when reading our index and merging.
arg_list.append("--reset")
# Handle non-trivial cases the way a real merge does.
arg_list.append("--aggressive")
# END merge handling
# tmp file created in git home directory to be sure renaming
# works - /tmp/ dirs could be on another device.
with contextlib.ExitStack() as stack:
tmp_index = stack.enter_context(_named_temporary_file_for_subprocess(repo.git_dir))
arg_list.append("--index-output=%s" % tmp_index)
arg_list.extend(treeish)
# Move current index out of the way - otherwise the merge may fail
# as it considers existing entries. Moving it essentially clears the index.
# Unfortunately there is no 'soft' way to do it.
# The TemporaryFileSwap ensures the original file gets put back.
stack.enter_context(TemporaryFileSwap(join_path_native(repo.git_dir, "index")))
repo.git.read_tree(*arg_list, **kwargs)
index = cls(repo, tmp_index)
index.entries # Force it to read the file as we will delete the temp-file.
return index
# END index merge handling
# UTILITIES
@unbare_repo
def _iter_expand_paths(self: "IndexFile", paths: Sequence[PathLike]) -> Iterator[PathLike]:
"""Expand the directories in list of paths to the corresponding paths accordingly.
:note:
git will add items multiple times even if a glob overlapped
with manually specified paths or if paths where specified multiple
times - we respect that and do not prune.
"""
def raise_exc(e: Exception) -> NoReturn:
raise e
r = str(self.repo.working_tree_dir)
rs = r + os.sep
for path in paths:
abs_path = str(path)
if not osp.isabs(abs_path):
abs_path = osp.join(r, path)
# END make absolute path
try:
st = os.lstat(abs_path) # Handles non-symlinks as well.
except OSError:
# The lstat call may fail as the path may contain globs as well.
pass
else:
if S_ISLNK(st.st_mode):
yield abs_path.replace(rs, "")
continue
# END check symlink
# If the path is not already pointing to an existing file, resolve globs if possible.
if not os.path.exists(abs_path) and ("?" in abs_path or "*" in abs_path or "[" in abs_path):
resolved_paths = glob.glob(abs_path)
# not abs_path in resolved_paths:
# a glob() resolving to the same path we are feeding it with
# is a glob() that failed to resolve. If we continued calling
# ourselves we'd endlessly recurse. If the condition below
# evaluates to true then we are likely dealing with a file
# whose name contains wildcard characters.
if abs_path not in resolved_paths:
for f in self._iter_expand_paths(glob.glob(abs_path)):
yield str(f).replace(rs, "")
continue
# END glob handling
try:
for root, _dirs, files in os.walk(abs_path, onerror=raise_exc):
for rela_file in files:
# Add relative paths only.
yield osp.join(root.replace(rs, ""), rela_file)
# END for each file in subdir
# END for each subdirectory
except OSError:
# It was a file or something that could not be iterated.
yield abs_path.replace(rs, "")
# END path exception handling
# END for each path
def _write_path_to_stdin(
self,
proc: "Popen",
filepath: PathLike,
item: PathLike,
fmakeexc: Callable[..., GitError],
fprogress: Callable[[PathLike, bool, PathLike], None],
read_from_stdout: bool = True,
) -> Union[None, str]:
"""Write path to proc.stdin and make sure it processes the item, including progress.
:return: stdout string
:param read_from_stdout: if True, proc.stdout will be read after the item
was sent to stdin. In that case, it will return None.
:note: There is a bug in git-update-index that prevents it from sending
reports just in time. This is why we have a version that tries to
read stdout and one which doesn't. In fact, the stdout is not
important as the piped-in files are processed anyway and just in time.
:note: Newlines are essential here, gits behaviour is somewhat inconsistent
on this depending on the version, hence we try our best to deal with
newlines carefully. Usually the last newline will not be sent, instead
we will close stdin to break the pipe.
"""
fprogress(filepath, False, item)
rval: Union[None, str] = None
if proc.stdin is not None:
try:
proc.stdin.write(("%s\n" % filepath).encode(defenc))
except IOError as e:
# Pipe broke, usually because some error happened.
raise fmakeexc() from e
# END write exception handling
proc.stdin.flush()
if read_from_stdout and proc.stdout is not None:
rval = proc.stdout.readline().strip()
fprogress(filepath, True, item)
return rval
def iter_blobs(
self, predicate: Callable[[Tuple[StageType, Blob]], bool] = lambda t: True
) -> Iterator[Tuple[StageType, Blob]]:
"""
:return: Iterator yielding tuples of Blob objects and stages, tuple(stage, Blob)
:param predicate:
Function(t) returning True if tuple(stage, Blob) should be yielded by the
iterator. A default filter, the BlobFilter, allows you to yield blobs
only if they match a given list of paths.
"""
for entry in self.entries.values():
blob = entry.to_blob(self.repo)
blob.size = entry.size
output = (entry.stage, blob)
if predicate(output):
yield output
# END for each entry
def unmerged_blobs(self) -> Dict[PathLike, List[Tuple[StageType, Blob]]]:
"""
:return:
Dict(path : list( tuple( stage, Blob, ...))), being
a dictionary associating a path in the index with a list containing
sorted stage/blob pairs.
:note:
Blobs that have been removed in one side simply do not exist in the
given stage. I.e. a file removed on the 'other' branch whose entries
are at stage 3 will not have a stage 3 entry.
"""
is_unmerged_blob = lambda t: t[0] != 0
path_map: Dict[PathLike, List[Tuple[StageType, Blob]]] = {}
for stage, blob in self.iter_blobs(is_unmerged_blob):
path_map.setdefault(blob.path, []).append((stage, blob))
# END for each unmerged blob
for line in path_map.values():
line.sort()
return path_map
@classmethod
def entry_key(cls, *entry: Union[BaseIndexEntry, PathLike, StageType]) -> Tuple[PathLike, StageType]:
return entry_key(*entry)
def resolve_blobs(self, iter_blobs: Iterator[Blob]) -> "IndexFile":
"""Resolve the blobs given in blob iterator.
This will effectively remove the index entries of the respective path at all
non-null stages and add the given blob as new stage null blob.
For each path there may only be one blob, otherwise a ValueError will be raised
claiming the path is already at stage 0.
:raise ValueError: if one of the blobs already existed at stage 0
:return: self
:note:
You will have to write the index manually once you are done, i.e.
``index.resolve_blobs(blobs).write()``.
"""
for blob in iter_blobs:
stage_null_key = (blob.path, 0)
if stage_null_key in self.entries:
raise ValueError("Path %r already exists at stage 0" % str(blob.path))
# END assert blob is not stage 0 already
# Delete all possible stages.
for stage in (1, 2, 3):
try:
del self.entries[(blob.path, stage)]
except KeyError:
pass
# END ignore key errors
# END for each possible stage
self.entries[stage_null_key] = IndexEntry.from_blob(blob)
# END for each blob
return self
def update(self) -> "IndexFile":
"""Reread the contents of our index file, discarding all cached information
we might have.
:note: This is a possibly dangerous operations as it will discard your changes
to index.entries.
:return: self
"""
self._delete_entries_cache()
# Allows to lazily reread on demand.
return self
def write_tree(self) -> Tree:
"""Write this index to a corresponding Tree object into the repository's
object database and return it.
:return: Tree object representing this index.
:note: The tree will be written even if one or more objects the tree refers to
does not yet exist in the object database. This could happen if you added
Entries to the index directly.
:raise ValueError: if there are no entries in the cache
:raise UnmergedEntriesError:
"""
# We obtain no lock as we just flush our contents to disk as tree.
# If we are a new index, the entries access will load our data accordingly.
mdb = MemoryDB()
entries = self._entries_sorted()
binsha, tree_items = write_tree_from_cache(entries, mdb, slice(0, len(entries)))
# Copy changed trees only.
mdb.stream_copy(mdb.sha_iter(), self.repo.odb)
# Note: Additional deserialization could be saved if write_tree_from_cache
# would return sorted tree entries.
root_tree = Tree(self.repo, binsha, path="")
root_tree._cache = tree_items
return root_tree
def _process_diff_args(
self, # type: ignore[override]
args: List[Union[str, "git_diff.Diffable", Type["git_diff.Diffable.Index"]]],
) -> List[Union[str, "git_diff.Diffable", Type["git_diff.Diffable.Index"]]]:
try:
args.pop(args.index(self))
except IndexError:
pass
# END remove self
return args
def _to_relative_path(self, path: PathLike) -> PathLike:
"""
:return: Version of path relative to our git directory or raise ValueError
if it is not within our git directory"""
if not osp.isabs(path):
return path
if self.repo.bare:
raise InvalidGitRepositoryError("require non-bare repository")
if not str(path).startswith(str(self.repo.working_tree_dir)):
raise ValueError("Absolute path %r is not in git repository at %r" % (path, self.repo.working_tree_dir))
return os.path.relpath(path, self.repo.working_tree_dir)
def _preprocess_add_items(
self, items: Sequence[Union[PathLike, Blob, BaseIndexEntry, "Submodule"]]
) -> Tuple[List[PathLike], List[BaseIndexEntry]]:
"""Split the items into two lists of path strings and BaseEntries."""
paths = []
entries = []
# if it is a string put in list
if isinstance(items, (str, os.PathLike)):
items = [items]
for item in items:
if isinstance(item, (str, os.PathLike)):
paths.append(self._to_relative_path(item))
elif isinstance(item, (Blob, Submodule)):
entries.append(BaseIndexEntry.from_blob(item))
elif isinstance(item, BaseIndexEntry):
entries.append(item)
else:
raise TypeError("Invalid Type: %r" % item)
# END for each item
return paths, entries
def _store_path(self, filepath: PathLike, fprogress: Callable) -> BaseIndexEntry:
"""Store file at filepath in the database and return the base index entry
Needs the git_working_dir decorator active ! This must be assured in the calling code"""
st = os.lstat(filepath) # Handles non-symlinks as well.
if S_ISLNK(st.st_mode):
# In PY3, readlink is a string, but we need bytes.
# In PY2, it was just OS encoded bytes, we assumed UTF-8.
open_stream: Callable[[], BinaryIO] = lambda: BytesIO(force_bytes(os.readlink(filepath), encoding=defenc))
else:
open_stream = lambda: open(filepath, "rb")
with open_stream() as stream:
fprogress(filepath, False, filepath)
istream = self.repo.odb.store(IStream(Blob.type, st.st_size, stream))
fprogress(filepath, True, filepath)
return BaseIndexEntry(
(
stat_mode_to_index_mode(st.st_mode),
istream.binsha,
0,
to_native_path_linux(filepath),
)
)
@unbare_repo
@git_working_dir
def _entries_for_paths(
self,
paths: List[str],
path_rewriter: Union[Callable, None],
fprogress: Callable,
entries: List[BaseIndexEntry],
) -> List[BaseIndexEntry]:
entries_added: List[BaseIndexEntry] = []
if path_rewriter:
for path in paths:
if osp.isabs(path):
abspath = path
gitrelative_path = path[len(str(self.repo.working_tree_dir)) + 1 :]
else:
gitrelative_path = path
if self.repo.working_tree_dir:
abspath = osp.join(self.repo.working_tree_dir, gitrelative_path)
# END obtain relative and absolute paths
blob = Blob(
self.repo,
Blob.NULL_BIN_SHA,
stat_mode_to_index_mode(os.stat(abspath).st_mode),
to_native_path_linux(gitrelative_path),
)
# TODO: variable undefined
entries.append(BaseIndexEntry.from_blob(blob))
# END for each path
del paths[:]
# END rewrite paths
# HANDLE PATHS
assert len(entries_added) == 0
for filepath in self._iter_expand_paths(paths):
entries_added.append(self._store_path(filepath, fprogress))
# END for each filepath
# END path handling
return entries_added
def add(
self,
items: Sequence[Union[PathLike, Blob, BaseIndexEntry, "Submodule"]],
force: bool = True,
fprogress: Callable = lambda *args: None,
path_rewriter: Union[Callable[..., PathLike], None] = None,
write: bool = True,
write_extension_data: bool = False,
) -> List[BaseIndexEntry]:
"""Add files from the working tree, specific blobs or BaseIndexEntries
to the index.
:param items:
Multiple types of items are supported, types can be mixed within one call.
Different types imply a different handling. File paths may generally be
relative or absolute.
- path string
Strings denote a relative or absolute path into the repository pointing
to an existing file, e.g., CHANGES, lib/myfile.ext,
'/home/gitrepo/lib/myfile.ext'.
Absolute paths must start with working tree directory of this index's
repository to be considered valid. For example, if it was initialized
with a non-normalized path, like ``/root/repo/../repo``, absolute paths
to be added must start with ``/root/repo/../repo``.
Paths provided like this must exist. When added, they will be written
into the object database.
PathStrings may contain globs, such as ``lib/__init__*``. Or they can be
directories like ``lib``, which will add all the files within the
directory and subdirectories.
This equals a straight git-add.
They are added at stage 0.
- Blob or Submodule object
Blobs are added as they are assuming a valid mode is set.
The file they refer to may or may not exist in the file system, but must
be a path relative to our repository.
If their sha is null (40*0), their path must exist in the file system
relative to the git repository as an object will be created from the
data at the path.
The handling now very much equals the way string paths are processed,
except that the mode you have set will be kept. This allows you to
create symlinks by settings the mode respectively and writing the target
of the symlink directly into the file. This equals a default
Linux-Symlink which is not dereferenced automatically, except that it
can be created on filesystems not supporting it as well.
Please note that globs or directories are not allowed in Blob objects.
They are added at stage 0.
- BaseIndexEntry or type
Handling equals the one of Blob objects, but the stage may be explicitly
set. Please note that Index Entries require binary sha's.
:param force:
**CURRENTLY INEFFECTIVE**
If True, otherwise ignored or excluded files will be added anyway.
As opposed to the git-add command, we enable this flag by default
as the API user usually wants the item to be added even though
they might be excluded.
:param fprogress:
Function with signature f(path, done=False, item=item) called for each
path to be added, one time once it is about to be added where done==False
and once after it was added where done=True.
item is set to the actual item we handle, either a Path or a BaseIndexEntry
Please note that the processed path is not guaranteed to be present
in the index already as the index is currently being processed.
:param path_rewriter:
Function with signature (string) func(BaseIndexEntry) function returning a
path for each passed entry which is the path to be actually recorded for the
object created from entry.path. This allows you to write an index which is
not identical to the layout of the actual files on your hard-disk. If not
None and ``items`` contain plain paths, these paths will be converted to
Entries beforehand and passed to the path_rewriter. Please note that
entry.path is relative to the git repository.
:param write:
If True, the index will be written once it was altered. Otherwise
the changes only exist in memory and are not available to git commands.
:param write_extension_data:
If True, extension data will be written back to the index. This can lead to
issues in case it is containing the 'TREE' extension, which will cause the
`git commit` command to write an old tree, instead of a new one representing
the now changed index.
This doesn't matter if you use :meth:`IndexFile.commit`, which ignores the
`TREE` extension altogether. You should set it to True if you intend to use
:meth:`IndexFile.commit` exclusively while maintaining support for
third-party extensions. Besides that, you can usually safely ignore the
built-in extensions when using GitPython on repositories that are not
handled manually at all.
All current built-in extensions are listed here:
http://opensource.apple.com/source/Git/Git-26/src/git-htmldocs/technical/index-format.txt
:return:
List(BaseIndexEntries) representing the entries just actually added.
:raise OSError:
If a supplied Path did not exist. Please note that BaseIndexEntry
Objects that do not have a null sha will be added even if their paths
do not exist.
"""
# Sort the entries into strings and Entries. Blobs are converted to entries automatically.
# Paths can be git-added. For everything else we use git-update-index.
paths, entries = self._preprocess_add_items(items)
entries_added: List[BaseIndexEntry] = []
# This code needs a working tree, therefore we try not to run it unless required.
# That way, we are OK on a bare repository as well.
# If there are no paths, the rewriter has nothing to do either.
if paths:
entries_added.extend(self._entries_for_paths(paths, path_rewriter, fprogress, entries))
# HANDLE ENTRIES
if entries:
null_mode_entries = [e for e in entries if e.mode == 0]
if null_mode_entries:
raise ValueError(
"At least one Entry has a null-mode - please use index.remove to remove files for clarity"
)
# END null mode should be remove
# HANDLE ENTRY OBJECT CREATION
# Create objects if required, otherwise go with the existing shas.
null_entries_indices = [i for i, e in enumerate(entries) if e.binsha == Object.NULL_BIN_SHA]
if null_entries_indices:
@git_working_dir
def handle_null_entries(self: "IndexFile") -> None:
for ei in null_entries_indices:
null_entry = entries[ei]
new_entry = self._store_path(null_entry.path, fprogress)
# Update null entry.
entries[ei] = BaseIndexEntry(
(
null_entry.mode,
new_entry.binsha,
null_entry.stage,
null_entry.path,
)
)
# END for each entry index
# END closure
handle_null_entries(self)
# END null_entry handling
# REWRITE PATHS
# If we have to rewrite the entries, do so now, after we have generated all object sha's.
if path_rewriter:
for i, e in enumerate(entries):
entries[i] = BaseIndexEntry((e.mode, e.binsha, e.stage, path_rewriter(e)))
# END for each entry
# END handle path rewriting
# Just go through the remaining entries and provide progress info.
for i, entry in enumerate(entries):
progress_sent = i in null_entries_indices
if not progress_sent:
fprogress(entry.path, False, entry)
fprogress(entry.path, True, entry)
# END handle progress
# END for each entry
entries_added.extend(entries)
# END if there are base entries
# FINALIZE
# Add the new entries to this instance.
for entry in entries_added:
self.entries[(entry.path, 0)] = IndexEntry.from_base(entry)
if write:
self.write(ignore_extension_data=not write_extension_data)
# END handle write
return entries_added
def _items_to_rela_paths(
self,
items: Union[PathLike, Sequence[Union[PathLike, BaseIndexEntry, Blob, Submodule]]],
) -> List[PathLike]:
"""Returns a list of repo-relative paths from the given items which
may be absolute or relative paths, entries or blobs."""
paths = []
# If string, put in list.
if isinstance(items, (str, os.PathLike)):
items = [items]
for item in items:
if isinstance(item, (BaseIndexEntry, (Blob, Submodule))):
paths.append(self._to_relative_path(item.path))
elif isinstance(item, (str, os.PathLike)):
paths.append(self._to_relative_path(item))
else:
raise TypeError("Invalid item type: %r" % item)
# END for each item
return paths
@post_clear_cache
@default_index
def remove(
self,
items: Sequence[Union[PathLike, Blob, BaseIndexEntry, "Submodule"]],
working_tree: bool = False,
**kwargs: Any,
) -> List[str]:
"""Remove the given items from the index and optionally from
the working tree as well.
:param items:
Multiple types of items are supported which may be be freely mixed.
- path string
Remove the given path at all stages. If it is a directory, you must
specify the r=True keyword argument to remove all file entries
below it. If absolute paths are given, they will be converted
to a path relative to the git repository directory containing
the working tree
The path string may include globs, such as \\*.c.
- Blob Object
Only the path portion is used in this case.
- BaseIndexEntry or compatible type
The only relevant information here Yis the path. The stage is ignored.
:param working_tree:
If True, the entry will also be removed from the working tree, physically
removing the respective file. This may fail if there are uncommitted changes
in it.
:param kwargs:
Additional keyword arguments to be passed to git-rm, such
as 'r' to allow recursive removal of
:return:
List(path_string, ...) list of repository relative paths that have
been removed effectively.
This is interesting to know in case you have provided a directory or
globs. Paths are relative to the repository.
"""
args = []
if not working_tree:
args.append("--cached")
args.append("--")
# Preprocess paths.
paths = self._items_to_rela_paths(items)